Hundreds of Millions of Hours of Video Content

There is an interesting article at the new York Times today about the new video search engine Blinkx.

Blinkx allows you to search inside the content of a video, not just the text associated with it. It’s a great idea, and will make searching for relevant video easier.

Blinkx’s speech-recognition technology employs neural networks and machine learning using “hidden Markov models,” a method of statistical analysis in which the hidden characteristics of a thing are guessed from what is known.

Amazing technology, from some very smart people.

The thing that gets me every time though, is search isn’t the only answer.

The difficulties of knowing which videos are where challenge the growth of Internet video. “If there are going to be hundreds of millions of hours of video content online,” Mr. Chandratillake said, “we need to have an efficient, scalable way to search through it.”

If there are hundreds of millions of hours of video content online, then it’s going to be next to impossible to search it quickly and easily. That’s why Scouta provides recommendations. Why search for a video when Scouta makes the suggestions based on what you’re interested in.